Zobrazeno 1 - 10
of 5 209
pro vyhledávání: '"Chellappa AS"'
Significant progress has been made in photo-realistic scene reconstruction over recent years. Various disparate efforts have enabled capabilities such as multi-appearance or large-scale modeling; however, there lacks a welldesigned dataset that can e
Externí odkaz:
http://arxiv.org/abs/2412.14418
Autor:
Lu, Taiming, Shu, Tianmin, Xiao, Junfei, Ye, Luoxin, Wang, Jiahao, Peng, Cheng, Wei, Chen, Khashabi, Daniel, Chellappa, Rama, Yuille, Alan, Chen, Jieneng
Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step toward this goal by introducing GenEx, a system capable of planning comp
Externí odkaz:
http://arxiv.org/abs/2412.09624
Autor:
Narayan, Kartik, Nair, Nithin Gopalakrishnan, Xu, Jennifer, Chellappa, Rama, Patel, Vishal M.
Pre-training on large-scale datasets and utilizing margin-based loss functions have been highly successful in training models for high-resolution face recognition. However, these models struggle with low-resolution face datasets, in which the faces l
Externí odkaz:
http://arxiv.org/abs/2412.07771
The discrete empirical interpolation method (DEIM) is a well-established approach, widely used for state reconstruction using sparse sensor/measurement data, nonlinear model reduction, and interpretable feature selection. We introduce the tensor t-pr
Externí odkaz:
http://arxiv.org/abs/2410.14519
Autor:
Rivera, Corban, Byrd, Grayson, Paul, William, Feldman, Tyler, Booker, Meghan, Holmes, Emma, Handelman, David, Kemp, Bethany, Badger, Andrew, Schmidt, Aurora, Jatavallabhula, Krishna Murthy, de Melo, Celso M, Seenivasan, Lalithkumar, Unberath, Mathias, Chellappa, Rama
Robotic planning and execution in open-world environments is a complex problem due to the vast state spaces and high variability of task embodiment. Recent advances in perception algorithms, combined with Large Language Models (LLMs) for planning, of
Externí odkaz:
http://arxiv.org/abs/2410.06108
Publikováno v:
Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II. Vol. 13035. SPIE, 2024
In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces to enable
Externí odkaz:
http://arxiv.org/abs/2410.02152
We introduce FusionRF, a novel neural rendering terrain reconstruction method from optically unprocessed satellite imagery. While previous methods depend on external pansharpening methods to fuse low resolution multispectral imagery and high resoluti
Externí odkaz:
http://arxiv.org/abs/2409.15132
Autor:
Nanduri, Anirudh, Chellappa, Rama
Despite the remarkable performance of deep neural networks for face detection and recognition tasks in the visible spectrum, their performance on more challenging non-visible domains is comparatively still lacking. While significant research has been
Externí odkaz:
http://arxiv.org/abs/2409.09832
Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to focus more on
Externí odkaz:
http://arxiv.org/abs/2409.00304
Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\text{inv}}$ where the conditional distribution $Y \mid X_{\te
Externí odkaz:
http://arxiv.org/abs/2407.18428